Container Use MCP — 설치 & 라이브 데모

왜 쓰나요

핵심 기능

One isolated container per agent task — no host pollution
Multiple agents work in parallel on the same repo via git worktrees inside containers
Replay, diff, and discard any environment after the fact
Pre-baked language images (node, python, go) or BYO Dockerfile
Works with Claude Code, Cursor, Goose, Aider through the same MCP layer

라이브 데모

실제 사용 모습

container-use-mcp.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "container-use-mcp": {
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "container-use-mcp": {
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "container-use-mcp": {
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "container-use-mcp": {
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "container-use-mcp",
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "container-use-mcp": {
      "command": {
        "path": "cu",
        "args": [
          "mcp"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add container-use-mcp -- cu mcp

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: Container Use

Try three refactoring approaches in parallel, keep the best

👤 Engineers exploring design space ⏱ ~15 min intermediate

언제 쓸까: You have 3 different ideas for a refactor and want to see all of them run/pass tests before picking one.

사전 조건

Server/skill installed and authenticated — See repo README

흐름

Spin up three isolated envs

Create three container-use environments named refactor-a/b/c, all on this repo at HEAD.✓ 복사됨

→ Three env_ids printed
Apply each approach in its own env

In refactor-a do the strategy-pattern version; in -b inline everything; in -c extract a service object. Run the full test suite in each. Report pass/fail and diff size.✓ 복사됨

→ Per-env test summary and diff stats
Pick the winner and merge

Apply the diff from refactor-b to my working copy. Discard the other two environments.✓ 복사됨

→ Patch applied locally

결과: Three real experiments evaluated side-by-side without ever breaking your host repo.

함정

Forgetting to discard old envs leaks disk — Forgetting to discard old envs leaks disk — cu environment list then cu environment discard <id> periodically.

함께 쓰기: github · filesystem

조합

다른 MCP와 조합해 10배 효율

container-use-mcp + github

Pair with github for complementary capabilities

Use this server together with github to complete a multi-step task.✓ 복사됨

container-use-mcp + filesystem

Pair with filesystem for complementary capabilities

Use this server together with filesystem to complete a multi-step task.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
environment_create	name: str, image: str	Start a fresh sandbox for the next task	Local CPU/disk
environment_run_cmd	env_id, cmd	Execute build/test commands inside the sandbox	free
environment_file_write	env_id, path, contents	Apply edits without touching the host	free
environment_diff	env_id	Review the agent's work before merging back	free

비용 및 제한

운영 비용

API 쿼터: See provider docs for rate limits
호출당 토큰: Varies by tool
금액: See repo README for pricing details
팁: Cache tool results and avoid repeated identical calls.

보안

권한, 시크릿, 파급범위

자격 증명 저장: Use environment variables; never commit secrets

데이터 외부 송신: Tool calls go to the provider's API as documented

문제 해결

자주 발생하는 오류와 해결

docker daemon not running

Container Use requires a local Docker or compatible runtime. Start Docker Desktop or colima.

확인: Run `docker ps` successfully

out of disk

Old environments aren't auto-pruned. Run cu environment list then cu environment discard <id> for anything older than a day.

확인: Check `docker system df`

대안

Container Use 다른 것과 비교

대안	언제 쓰나	단점/장점
Dagger Cloud	You want hosted, multi-tenant agent envs	Paid; container-use is local-first

Container Use